skip to main content
US FlagAn official website of the United States government
dot gov icon
Official websites use .gov
A .gov website belongs to an official government organization in the United States.
https lock icon
Secure .gov websites use HTTPS
A lock ( lock ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

Explore Research Products in the PAR
It may take a few hours for recently added research products to appear in PAR search results.


Title: Dazzle: Using Optimized Generative Adversarial Networks to Address Security Data Class Imbalance Issue
Background: Machine learning techniques have been widely used and demonstrate promising performance in many software security tasks such as software vulnerability prediction. However, the class ratio within software vulnerability datasets is often highly imbalanced (since the percentage of observed vulnerability is usually very low). Goal: To help security practitioners address software security data class imbalanced issues and further help build better prediction models with resampled datasets. Method: We introduce an approach called Dazzle which is an optimized version of conditional Wasserstein Generative Adversarial Networks with gradient penalty (cWGAN-GP). Dazzle explores the architecture hyperparameters of cWGAN-GP with a novel optimizer called Bayesian Optimization. We use Dazzle to generate minority class samples to resample the original imbalanced training dataset. Results: We evaluate Dazzle with three software security datasets, i.e., Moodle vulnerable files, Ambari bug reports, and JavaScript function code. We show that Dazzle is practical to use and demonstrates promising improvement over existing state-of-the-art oversampling techniques such as SMOTE (e.g., with an average of about 60% improvement rate over SMOTE in recall among all datasets). Conclusion: Based on this study, we would suggest the use of optimized GANs as an alternative method for security vulnerability data class imbalanced issues.  more » « less
Award ID(s):
1909516
PAR ID:
10358639
Author(s) / Creator(s):
; ; ;
Date Published:
Journal Name:
2022 IEEE/ACM 19th International Conference on Mining Software Repositories (MSR)
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. ; ; ; ; (, Proceedings of the SIAM International Conference on Data Mining)
    In many real-world classification applications such as fake news detection, the training data can be extremely imbalanced, which brings challenges to existing classifiers as the majority classes dominate the loss functions of classifiers. Oversampling techniques such as SMOTE are effective approaches to tackle the class imbalance problem by producing more synthetic minority samples. Despite their success, the majority of existing oversampling methods only consider local data distributions when generating minority samples, which can result in noisy minority samples that do not fit global data distributions or interleave with majority classes. Hence, in this paper, we study the class imbalance problem by simultaneously exploring local and global data information since: (i) the local data distribution could give detailed information for generating minority samples; and (ii) the global data distribution could provide guidance to avoid generating outliers or samples that interleave with majority classes. Specifically, we propose a novel framework GL-GAN, which leverages the SMOTE method to explore local distribution in a learned latent space and employs GAN to capture the global information, so that synthetic minority samples can be generated under even extremely imbalanced scenarios. Experimental results on diverse real data sets demonstrate the effectiveness of our GL-GAN framework in producing realistic and discriminative minority samples for improving the classification performance of various classifiers on imbalanced training data. Our code is available at https://github.com/wentao-repo/GL-GAN. 
    more » « less
  2. ; ; ; ; ; ; (, Empirical software engineering)
    Context: Applying vulnerability detection techniques is one of many tasks using the limited resources of a software project. Objective: The goal of this research is to assist managers and other decision- makers in making informed choices about the use of software vulnerability detection techniques through an empirical study of the efficiency and effectiveness of four techniques on a Java-based web application. Method: We apply four different categories of vulnerability detection techniques – systematic manual penetration testing (SMPT), exploratory manual penetration testing (EMPT), dynamic application security testing (DAST), and static application security testing (SAST) – to an open-source medical records system. Results: We found the most vulnerabilities using SAST. However, EMPT found more severe vulnerabilities. With each technique, we found unique vulnerabilities not found using the other techniques. The efficiency of manual techniques (EMPT, SMPT) was comparable to or better than the efficiency of automated techniques (DAST, SAST) in terms of Vulnerabilities per Hour (VpH). Conclusions: The vulnerability detection technique practitioners should select may vary based on the goals and available resources of the project. If the goal of an organization is to find “all” vulnerabilities in a project, they need to use as many techniques as their resources allow. 
    more » « less
  3. ; ; (, Society for Industrial and Applied Mathematics)
    Biased AI models result in unfair decisions. In response, a number of algorithmic solutions have been engineered to mitigate bias, among which the Synthetic Minority Oversampling Technique (SMOTE) has been studied, to an extent. Although the SMOTE technique and its variants have great potentials to help improve fairness, there is little theoretical justification for its success. In addition, formal error and fairness bounds are not clearly given. This paper attempts to address both issues. We prove and demonstrate that synthetic data generated by oversampling underrepresented groups can mitigate algorithmic bias in AI models, while keeping the predictive errors bounded. We further compare this technique to the existing state-of-the-art fair AI techniques on five datasets using a variety of fairness metrics. We show that this approach can effectively improve fairness even when there is a significant amount of label and selection bias, regardless of the baseline AI algorithm. 
    more » « less
  4. ; ; ; (, Advances in neural information processing systems)
    We propose a novel unsupervised generative model that learns to disentangle object identity from other low-level aspects in class-imbalanced data. We first investigate the issues surrounding the assumptions about uniformity made by InfoGAN [10], and demonstrate its ineffectiveness to properly disentangle object identity in imbalanced data. Our key idea is to make the discovery of the discrete latent factor of variation invariant to identity-preserving transformations in real images, and use that as a signal to learn the appropriate latent distribution representing object identity. Experiments on both artificial (MNIST, 3D cars, 3D chairs, ShapeNet) and real-world (YouTube-Faces) imbalanced datasets demonstrate the effectiveness of our method in disentangling object identity as a latent factor of variation. 
    more » « less
  5. ; ; (, The Astrophysical Journal Supplement Series)
    Abstract The accurate prediction of solar flares is crucial due to their risks to astronauts, space equipment, and satellite communication systems. Our research enhances solar flare prediction by employing sophisticated data preprocessing and sampling techniques for the Space Weather Analytics for Solar Flares (SWAN-SF) data set, a rich source of multivariate time series data of solar active regions. Our study adopts a multifaceted approach encompassing four key methodologies. Initially, we address over 10 million missing values in the SWAN-SF data set through our innovative imputation technique called fast Pearson correlation-based k-nearest neighbors imputation. Subsequently, we propose a precise normalization technique, called LSBZM normalization, tailored for time series data, merging various strategies (log, square root, Box–Cox, Z-score, and min–max) to uniformly scale the data set's 24 attributes (photospheric magnetic field parameters), addressing issues such as skewness. We also explore the “near decision boundary sample removal” technique to enhance the classification performance of the data set by effectively resolving the challenge of class overlap. Finally, a pivotal aspect of our research is a thorough evaluation of diverse oversampling and undersampling methods, including SMOTE, ADASYN, Gaussian noise injection, TimeGAN, Tomek links, and random undersampling, to counter the severe imbalance in the SWAN-SF data set, notably a 60:1 ratio of major (X and M) to minor (C, B, and FQ) flaring events in binary classification. To demonstrate the effectiveness of our methods, we use eight classification algorithms, including advanced deep-learning-based architectures. Our analysis shows significant true skill statistic scores, underscoring the importance of data preprocessing and sampling in time-series-based solar flare prediction. 
    more » « less
  • Citation Formats
  • MLA
  • APA
  • Chicago
  • BibTeX
  • Save / Share this Record
  • Send to Email